Below is the list of the abstracts accepted to the 2020 WiNLP workshop. Congratulations to all authors!
WiNLP is non-archival. Abstracts will be made available through a short period under certain restrictions.
Please contact the authors directly if you are interested in the abstract.
Note: All papers available here meet the WiNLP 2020 format and style guidelines (and 3 pages length + unlimited references).
If your paper is not listed, please validate the format and then get in touch with the WiNLP organization.
- Corpus-based Amharic sentiment lexicon generation, Girma Neshir Alemneh, Andreas Rauber, and Solomon Atnafu
- Negation handling for Amharic sentiment classification, Girma Neshir Alemneh, Andreas Rauber, and Solomon Atnafu
- Embedding Oriented Adaptable Semantic Annotation Framework for Amharic Web Documents, Kidane Woldemariyam, and Dr. Fekade Getahun
- Similarity and Fairness Based Bidirectional Neural Co-Attention for Amharic Natural Language Inference, Abebaw Eshetu, Getenesh Teshome, and Ribka Alemayehu
- Large Vocabulary Read Speech Corpora for Four Ethiopian Languages: Amharic, Tigrigna, Oromo, and Wolaytta, Solomon Teferra Abate, Martha Yifiru Tachbelie, Michael Melese, Hafte Abera, Tewodros Gebreselassie, Wondwossen Mulugeta, Yaregal Assabie, Million Meshesha Beyene, Solomon Atinafu and Binyam Ephrem Seyoum
- SIMPLEX-PB 2.0: A Reliable Dataset for Lexical Simplification in Brazilian Portuguese, Nathan Hartmann, Gustavo Henrique Paetzold, and Sandra Aluísio
- Anonymized paper (by request), Reyhaneh Hashempour and Aline Villavicencio
- Bi-directional Answer-to-Answer Co-attention for Short Answer Grading using Deep Learning, Abebaw Eshetu, Getenesh Teshome, and Ribka Alemahu
- Effective questions in referential visual dialog, Mauricio Mazuecos, Alberto Testoni, Raffaella Bernardi, and Luciana Benotti
- A Translation-Based Approach to Morphology Learning for Low Resource Languages, Tewodros Gebreselassie, Amanuel Mersha, and Michael Gasser
- Tigrinya Automatic Speech recognition with Morpheme based recognition units, Hafte Abera, and Sebsibe Hailemariam
- Variants of Vector Space Reductions for Predicting the Compositionality of English Noun Compounds, Pegah Alipoormolabashi and Sabine Schulte im Walde
- Anonymized paper (by request), David Kabiito and Joyce Nakatumba Nabende
- An Assessment of Language Identification Methods on Tweets and Wikipedia Articles, Pedro Vernetti and Larissa Freitas
- A Comparison of Identification Methods of Brazilian Music Styles by Lyrics, Patrick Guimarães, Jader Froes, Douglas Costa, and Larissa Freitas
- Enabling fast and correct typing in ‘Leichte Sprache’ (Easy Language), Ina Steinmetz and Karin Harbusch
- SkillBERT: “Skilling” the BERT to classify skills!, Amber Nigam, Shikha Tyagi, Kuldeep Dhakar, and Arpan Saxena
- AI4D – African Language Dataset Challenge, Kathleen Siminyu, and Sackey Freshia
- Can Wikipedia Categories Improve Masked Language Model Pretraining?, Diksha Meghwal, Katharina Kann, Iacer Calixto, and Stanislaw Jastrzebski
- Adversarial Evaluation of BERT for Biomedical Named Entity Recognition, Vladimir Araujo, Andrés Carvallo, and Denis Parra
- FFR v1.1 : Fon-French Neural Machine Translation, Chris Chinenye Emezue and Femi Pancrace Bonaventure Dossou
- Corpus Development for Indonesian Product Named Entity Recognition using Semi-supervised Approach, Muhammad Akmal and Ade Romadhony
- Classification and Analysis of Neologisms Produced by Learners of Spanish: Effects of Proficiency and Task, Shira Wein
- Developing a Monolingual Sentence Simplification Corpus for Urdu, Yusra Anees, Sadaf Abdul Rauf, Nauman Iqbal, and Abdul Basit Siddiqi
- Personality Trait Detection Using Bagged SVM over BERT Word Embedding Ensembles, Amirmohammad Kazemeini, Samin Fatehi, Yash Mehta, Sauleh Eetemadi, and Erik Cambria
- Translating Natural Language Instructions for Behavioral Robot Navigation with a Multi-Head Attention Mechanism, Patricio Cerda-Mardini, Vladimir Araujo, and Álvaro Soto
- Towards Mitigating Gender Bias in a decoder-based Neural Machine Translation model by Adding Contextual Information, Christine Basta, Marta R. Costa-jussà, and José A. R. Fonollosa
- Predicting and Analyzing Law-Making in Kenya, Oyinlola Babafemi and Adewale Akinfaderin
- Defining and Evaluating Fair Natural Language Generation, Catherine Yeo, and Alyssa Chen
- Political Advertising Dataset: the use case of the Polish 2020 Presidential Elections, Lukasz Augustyniak, Krzysztof Rajda, Tomasz Kajdanowicz and Michał Bernaczyk
- Addressing Challenges of Indigenous Languages through Neural Machine Translation: The case of Inuktitut-English, Tan Ngoc Le and Fatiha Sadat
- The human unlikeness of neural language models in next-word prediction, Cassandra L. Jacobs and Arya D. McCarthy
- A Study on the Influence of Architecture Complexity of RNNs for Intent Classification in E-Commerce Chats in Bahasa Indonesia, Renny Pradina Kusumawardani and Muhammad Azzam
- Long-Tail Predictions with Continuous-Output Language Models, Shiran Dudy and Steven Bedrick
- Analyzing the Framing of 2020 Presidential Candidates in the News, Audrey Acken, and Dorottya Demszky
- Understanding the Impact of Experiment Design for Evaluating Dialogue System Output, Sashank Santhanam and Samira Shaikh
- Studying The Effect of Emotional and Moral Language on Information Contagion during the Charlottesville Event, Khyati Mahajan, Sara Levens, Tiffany Gallicano, and Samira Shaikh
- Multitask Models for Controlling the Complexity of Neural Machine Translation, Sweta Agrawal and Marine Carpuat
- Using Social Media For Bitcoin Day Trading Behavior Prediction, Anna Paula Pawlicka Maule and Kristen Johnson
- Outcomes of coming out: Analyzing stories of LGBTQ+, Krithika Ramesh and Tanvi Anand
- An Evaluation of Subword Segmentation Strategies for Neural Machine Translation of Morphologically Rich Languages, Aquia Richburg, Ramy Eskander, Smaranda Muresan, and Marine Carpuat
- Enhanced Urdu Word Segmentation using Conditional Random Fields and Morphological Context Features, Aamir Farhan, Mashrukh Islam, and Dipti Misra Sharma
- 66 – Anonymized paper (by request), Anonymized authors